Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205757056> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4205757056 abstract "Protecting privileged communications and data from inadvertent disclosure is a paramount task in the US legal practice. Traditionally counsels rely on keyword searching and manual review to identify privileged documents in cases. As data volumes increase, this approach becomes less and less defensible in costs. Machine learning methods have been used in identifying privilege documents. Given the generalizable nature of privilege in legal cases, we hypothesize that transfer learning can capitalize knowledge learned from existing labeled data to identify privilege documents without requiring labeling new training data. In this paper, we study both traditional machine learning models and deep learning models based on BERT for privilege document classification tasks in legal document review, and we examine the effectiveness of transfer learning in privilege model on three real world datasets with privilege labels. Our results show that BERT model outperforms the industry standard logistic regression algorithm and transfer learning models can achieve decent performance on datasets in same or close domains." @default.
- W4205757056 created "2022-01-26" @default.
- W4205757056 creator A5032717078 @default.
- W4205757056 creator A5053350610 @default.
- W4205757056 creator A5078200110 @default.
- W4205757056 date "2021-12-15" @default.
- W4205757056 modified "2023-10-14" @default.
- W4205757056 title "An Empirical Study on Transfer Learning for Privilege Review" @default.
- W4205757056 cites W1997260010 @default.
- W4205757056 cites W2029075138 @default.
- W4205757056 cites W2585689263 @default.
- W4205757056 cites W2912770177 @default.
- W4205757056 cites W2953958347 @default.
- W4205757056 cites W3007156589 @default.
- W4205757056 cites W3106092787 @default.
- W4205757056 cites W3118485687 @default.
- W4205757056 cites W3138482863 @default.
- W4205757056 cites W3156899621 @default.
- W4205757056 doi "https://doi.org/10.1109/bigdata52589.2021.9672008" @default.
- W4205757056 hasPublicationYear "2021" @default.
- W4205757056 type Work @default.
- W4205757056 citedByCount "1" @default.
- W4205757056 countsByYear W42057570562022 @default.
- W4205757056 crossrefType "proceedings-article" @default.
- W4205757056 hasAuthorship W4205757056A5032717078 @default.
- W4205757056 hasAuthorship W4205757056A5053350610 @default.
- W4205757056 hasAuthorship W4205757056A5078200110 @default.
- W4205757056 hasConcept C119857082 @default.
- W4205757056 hasConcept C127413603 @default.
- W4205757056 hasConcept C150899416 @default.
- W4205757056 hasConcept C154945302 @default.
- W4205757056 hasConcept C201995342 @default.
- W4205757056 hasConcept C204321447 @default.
- W4205757056 hasConcept C2780138299 @default.
- W4205757056 hasConcept C2780451532 @default.
- W4205757056 hasConcept C38652104 @default.
- W4205757056 hasConcept C41008148 @default.
- W4205757056 hasConceptScore W4205757056C119857082 @default.
- W4205757056 hasConceptScore W4205757056C127413603 @default.
- W4205757056 hasConceptScore W4205757056C150899416 @default.
- W4205757056 hasConceptScore W4205757056C154945302 @default.
- W4205757056 hasConceptScore W4205757056C201995342 @default.
- W4205757056 hasConceptScore W4205757056C204321447 @default.
- W4205757056 hasConceptScore W4205757056C2780138299 @default.
- W4205757056 hasConceptScore W4205757056C2780451532 @default.
- W4205757056 hasConceptScore W4205757056C38652104 @default.
- W4205757056 hasConceptScore W4205757056C41008148 @default.
- W4205757056 hasLocation W42057570561 @default.
- W4205757056 hasOpenAccess W4205757056 @default.
- W4205757056 hasPrimaryLocation W42057570561 @default.
- W4205757056 hasRelatedWork W2081647779 @default.
- W4205757056 hasRelatedWork W2960456850 @default.
- W4205757056 hasRelatedWork W3107474891 @default.
- W4205757056 hasRelatedWork W3185852197 @default.
- W4205757056 hasRelatedWork W4213299466 @default.
- W4205757056 hasRelatedWork W4281382123 @default.
- W4205757056 hasRelatedWork W4281645081 @default.
- W4205757056 hasRelatedWork W4308262314 @default.
- W4205757056 hasRelatedWork W4318834068 @default.
- W4205757056 hasRelatedWork W4318957922 @default.
- W4205757056 isParatext "false" @default.
- W4205757056 isRetracted "false" @default.
- W4205757056 workType "article" @default.